cursor-agent-tr: Command for Claude Code

.cursor/commands/proje_orkestra.md

proje_orkestra is a command for Claude Code, Cursor from KayaErhan/cursor-agent-tr. It costs 0 tokens per session (1,218 once invoked), scanned A, original, MIT.

A command that coordinates a project through planned development phases and repeated work batches.

In plain words
What is it for?
Use it to resume project state, select appropriate agents or fallback instructions, process TODO tasks in waves, and continue until each phase meets its completion rules.
Why use it?
It helps keep discovery, design, coding, gap checks, testing, quality review, security review, and completion in the intended order.

Command for Claude CodeCursor

Written for Cursor and Claude Code: installed under .cursor/, but also a Claude Code command (commands/*.md). Also seen: mentions subagents.

This is KayaErhan/cursor-agent-tr's own configuration. It tells Claude Code and Cursor how to work on cursor-agent-tr itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything cursor-agent-tr configures →

Reuse

Borrowing it

Nothing to install: this file belongs to KayaErhan/cursor-agent-tr. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/KayaErhan/cursor-agent-tr/main/.cursor/commands/proje_orkestra.md
Clone the repo
git clone --depth 1 https://github.com/KayaErhan/cursor-agent-tr

Made for: Claude Code, Cursor.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for proje_orkestra

README.md
[![agentmods](https://agentmods.dev/badge/commands/kayaerhan/cursor-agent-tr/proje_orkestra/github.svg)](https://agentmods.dev/commands/kayaerhan/cursor-agent-tr/proje_orkestra)
Your own site
<a href="https://agentmods.dev/commands/kayaerhan/cursor-agent-tr/proje_orkestra"><img src="https://agentmods.dev/badge/commands/kayaerhan/cursor-agent-tr/proje_orkestra/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for proje_orkestra

Your own site · 80×15
<a href="https://agentmods.dev/commands/kayaerhan/cursor-agent-tr/proje_orkestra"><img src="https://agentmods.dev/badge/commands/kayaerhan/cursor-agent-tr/proje_orkestra.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,218 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01218
Opus 5 $0.00000 $0.00609
Sonnet 5 $0.00000 $0.00244
Haiku 4.5 $0.00000 $0.00122

Measured 10d ago against content hash 385d36612915, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

proje_orkestra scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.cursor/commands/proje_orkestra.md · 119 lines

How it starts

The opening of the file, as written. The whole thing — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/proje_orkestra — Orkestra Agent Sistemi v2 (Ana Komut)

Tek komutla projeyi planlanmis fazlarda ilerletir; TODO maddelerini dalga dalga isler; tek-iki gorev yapip durmaz.

Mimari: docs/ORCHESTRATION_ARCHITECTURE.md | Sozlesmeler: docs/AGENT_CONTRACTS.md


Kim cagirir

Ana agent (Orkestra Sefi) bu komutu alinca asagiyi ayni oturumda uygular.

Subagent cagirma (Cursor native)

  1. .cursor/agents/ altindaki rol dosyasini oku (frontmatter name + description).
  2. Uygun rol icin Task araci ile subagent baslat (or. project-discovery-agent, implementation-agent).
  3. Paralel: birbirinden bagimsiz modul gorevlerinde birden fazla Task; ayni dosyada paralel yazma yok.
  4. Subagent yoksa veya Task basarisiz: WORKFLOW_STATE.orchestration_mode = "fallback"; ayni rol talimatini ana agent sirayla uygular.

Native subagent yoksa orchestration_mode: fallback ile ayni rolleri simule et.


0) Resume (her cagrida zorunlu)

  1. git status — dogrulanmamis degisiklikler
  2. docs/WORKFLOW_STATE.md (schema v2)
  3. docs/TODO.md — hazir / devam / kritik sayilari
  4. Son TEST, GAP, QUALITY, SECURITY raporlari
  5. Kod vs TODO mutabakati
  6. progress-state-agent mantigi: resume_from guncelle

1) Dalga kotasi (KRITIK — tek madde durma yasagi)

Implementasyon / continue fazinda:

  • Minimum 3, uygunsa 5 hazir TODO gorevini aynı dalgada isle.
  • Bir gorev bittikten sonra kullaniciya "devam edeyim mi?" sorma.
  • Durdurma yalnizca:
    • Faz DoD tamamlandi
    • Dalga kotasi doldu ve sonraki hazir gorev yok
    • Gercek blocker (veri kaybi, odeme, secret, celisen urun karari)
    • Ayni hata 3 retry sonrasi Bloke

Her dalga sonu: build/lint/typecheck/test (projede tanimliysa) + todo-controller-agent mutabakat.


2) Faz sirasi

analysisdesigndevgap_scancontinuetestquality_gatesecurityfinish

Faz Subagent / komut mantigi
analysis project-discovery-agent + proje_incele.md
design ui-ux-design-agent + proje_tasarim.md
dev software-architect-agent (plan) + implementation-agent dalgalari
gap_scan proje_eksik_tara.md + completion-auditor on tarama
continue implementation-agent; dalga kotasi 3–5
test test-qa-agent + proje_test.md
quality_gate security-quality-agent + proje_kalite_kapisi.md
security proje_guvenlik_tara.md
finish completion-auditor onay → documentation-release-agent + proje_bitir.md

Read the full file on GitHub · 119 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 119 lines · 0 tokens per session scan A 385d36612915

Subscribe to this mod's changes

proje_orkestra is a command published in the GitHub repository KayaErhan/cursor-agent-tr (6 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,218 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.